Learning Gradient Fields for Molecular Conformation Generation

Authors: Chence Shi, Shitong Luo, Minkai Xu, Jian Tang

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results across multiple tasks show that Conf GF outperforms previous state-of-the-art baselines by a significant margin. The code is available at https://github.com/ Deep Graph Learning/Conf GF.
Researcher Affiliation Academia 1Mila Quebec AI Institute, Montr eal, Canada 2University of Montr eal, Montr eal, Canada 3Peking University 4CIFAR AI Research Chair 5HEC Montr eal, Montr eal, Canada.
Pseudocode Yes Algorithm 1 Annealed Langevin dynamics sampling
Open Source Code Yes The code is available at https://github.com/ Deep Graph Learning/Conf GF.
Open Datasets Yes Following Xu et al. (2021), we use the GEOM-QM9 and GEOM-Drugs (Axelrod & Gomez-Bombarelli, 2020) datasets for the conformation generation task... We evaluate the distance modeling task on the ISO17 dataset (Simm & Hernandez-Lobato, 2020).
Dataset Splits No The paper specifies a training set and a test set, but does not explicitly mention a validation set or a specific split for it.
Hardware Specification Yes The model is optimized with Adam (Kingma & Ba, 2014) optimizer on a single Tesla V100 GPU.
Software Dependencies No The paper mentions "Conf GF is implemented in Pytorch (Paszke et al., 2017)", but does not specify a version number for PyTorch or any other software dependencies.
Experiment Setup Yes The GINs is implemented with N = 4 layers and the hidden dimension is set as 256 across all modules. For training, we use an exponentially-decayed learning rate starting from 0.001 with a decay rate of 0.95. The model is optimized with Adam (Kingma & Ba, 2014) optimizer on a single Tesla V100 GPU. All hyperparameters related to noise levels as well as annealed Langevin dynamics are selected according to Song & Ermon (2020).